[AMDGPU][Waitcnts] Don't create a pending flat event for LDS DMA #170263
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Flat instructions need a waitcnt(0) on both VMEM and LDS accesses, but only when the instruction really is using flat addressing. The LDS DMA instructions (on GFX9) have the FLAT flag set, but they have very clear semantics. These instructions update only VM_CNT (on GFX9), and hence do not need to be treated like actual flat instructions.
Pierre-vh
approved these changes
Dec 2, 2025
jayfoad
reviewed
Dec 4, 2025
| // - it will require that both the VM and LGKM be flushed to zero if it is | ||
| // pending when a VM or LGKM dependency occurs. | ||
| if (FlatASCount > 1) | ||
| // If this is a truly flat memory operation, then it accesss both VMEM and |
Comment on lines
+2298
to
+2299
| // For example, LDS DMA operations have FLAT set in their TSFlags for | ||
| // unspecified reasons, but they are not flat operations) |
Contributor
There was a problem hiding this comment.
FLAT in TSFlags means they use FLAT encoding, which is true for all FLAT_* GLOBAL_* and SCRATCH_* instructions.
kcloudy0717
pushed a commit
to kcloudy0717/llvm-project
that referenced
this pull request
Dec 4, 2025
…m#170263) Flat instructions need a waitcnt(0) on both VMEM and LDS accesses, but only when the instruction really is using flat addressing. The LDS DMA instructions (on GFX9) have the FLAT flag set, but they have very clear semantics. These instructions update only VM_CNT (on GFX9), and hence do not need to be treated like actual flat instructions.
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
3 participants
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Flat instructions need a waitcnt(0) on both VMEM and LDS accesses, but only when the instruction really is using flat addressing. The LDS DMA instructions (on GFX9) have the FLAT flag set, but they have very clear semantics. These instructions update only VM_CNT (on GFX9), and hence do not need to be treated like actual flat instructions.